Saturday, 31 October 2026 · Weekend classic from 2022 · 5 min read
Chain-of-thought prompting improves reasoning in large language models
Providing large language models with few-shot exemplars that include intermediate reasoning steps, called chain-of-thought prompting, significantly boosts their performance on arithmetic, commonsense, and symbolic reasoning tasks, achieving state-of-the-art results without finetuning.
Based on the paper Chain-of-Thought Prompting Elicits Reasoning in Large Language Models by Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma and 5 others
Challenges in eliciting reasoning from large language models
Large language models have improved dramatically with scale, but their ability to perform complex reasoning tasks such as arithmetic, commonsense, and symbolic reasoning remains limited when using standard prompting methods.
Previous approaches to improve reasoning involved training models to generate rationales or fine-tuning on datasets with intermediate steps, but these require costly annotations and retraining.
Few-shot prompting allows models to learn tasks from a few examples without finetuning, but standard few-shot prompting often fails on reasoning tasks and does not improve much with larger model size.
Sign in to read the whole paper
You have read the opening. The rest is free with a Bezen account, and no card is needed.
In the rest of this paper
- How the method works, step by step, with a flow chart
- Two figures from the paper, and how to read them
- How it was tested, what was found, and where it falls short